ATRNet-LUDO provides 121k multi-view UAV images and a JEPA world-model policy that improves generalization for active object detection over standard DRL.
Deep residual learning for image recognition
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
HyDeS introduces hyperspherical density shaping with a von Mises-Fisher estimator to create theoretically grounded self-supervised representations that focus on foreground features.
Anisotropic self-supervised vision representations degrade approximate nearest-neighbor retrieval performance while more isotropic ones with local purity improve it.
A learned dispatcher picks among pre-trained DNNs per input and reports up to 36% fewer operations with comparable accuracy on several benchmarks.
An edge-cloud UAV inspection system with a new lightweight detector (EdgeAnt) and keyframe selection reduces end-to-end latency by 88.9% and reports 42.1% mAP on a custom antenna dataset.
citing papers explorer
-
Toward Active Object Detection for UAVs in the Wild: A Large-Scale Dataset, Benchmark and Method
ATRNet-LUDO provides 121k multi-view UAV images and a JEPA world-model policy that improves generalization for active object detection over standard DRL.
-
Self-Supervised Representation Learning via Hyperspherical Density Shaping
HyDeS introduces hyperspherical density shaping with a von Mises-Fisher estimator to create theoretically grounded self-supervised representations that focus on foreground features.
-
Geometric Analysis of Self-Supervised Vision Representations for Semantic Image Retrieval
Anisotropic self-supervised vision representations degrade approximate nearest-neighbor retrieval performance while more isotropic ones with local purity improve it.
-
PERTINENCE: Input-based Opportunistic Neural Network Dynamic Execution
A learned dispatcher picks among pre-trained DNNs per input and reports up to 36% fewer operations with comparable accuracy on several benchmarks.
-
Real-Time AIoT for AAV Antenna Interference Detection via Edge-Cloud Collaboration
An edge-cloud UAV inspection system with a new lightweight detector (EdgeAnt) and keyframe selection reduces end-to-end latency by 88.9% and reports 42.1% mAP on a custom antenna dataset.